© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126319
    Prev
    Next
    INDEX
    Explanations

    code/web snippets

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the header keywords “Received” and “Request,” flagging those administrative field tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的一个
    -0.07
    属性
    -0.07
    �
    -0.06
    Bah
    -0.06
    .is
    -0.06
    ADER
    -0.06
     frustrated
    -0.06
     respect
    -0.06
    _DEFIN
    -0.06
    :border
    -0.06
    POSITIVE LOGITS
     prima
    0.07
    orgot
    0.06
     Advantage
    0.06
     yıl
    0.06
     Workspace
    0.06
     Sofa
    0.06
     inte
    0.06
    ologické
    0.06
     Chatt
    0.06
     missed
    0.06
    Activations Density 0.000%

    No Known Activations